1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
|
# -*- coding: utf-8 -*-
# Copyright 2019-2025 Mike Fährmann
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation.
"""Extractors for https://imgbb.com/"""
from .common import Extractor, Message
from .. import text, util, exception
from ..cache import cache
class ImgbbExtractor(Extractor):
"""Base class for imgbb extractors"""
category = "imgbb"
directory_fmt = ("{category}", "{user}")
filename_fmt = "{title} {id}.{extension}"
archive_fmt = "{id}"
root = "https://imgbb.com"
def __init__(self, match):
Extractor.__init__(self, match)
self.page_url = self.sort = None
def items(self):
self.login()
url = self.page_url
params = {"sort": self.sort}
while True:
response = self.request(url, params=params, allow_redirects=False)
if response.status_code < 300:
break
url = response.headers["location"]
if url.startswith(self.root):
raise exception.NotFoundError(self.subcategory)
page = response.text
data = self.metadata(page)
first = True
for img in self.images(page):
image = {
"id" : img["url_viewer"].rpartition("/")[2],
"user" : img["user"]["username"] if "user" in img else "",
"title" : text.unescape(img["title"]),
"url" : img["image"]["url"],
"extension": img["image"]["extension"],
"size" : text.parse_int(img["image"]["size"]),
"width" : text.parse_int(img["width"]),
"height" : text.parse_int(img["height"]),
}
image.update(data)
if first:
first = False
yield Message.Directory, data
yield Message.Url, image["url"], image
def login(self):
username, password = self._get_auth_info()
if username:
self.cookies_update(self._login_impl(username, password))
@cache(maxage=365*86400, keyarg=1)
def _login_impl(self, username, password):
self.log.info("Logging in as %s", username)
url = self.root + "/login"
page = self.request(url).text
token = text.extr(page, 'PF.obj.config.auth_token="', '"')
headers = {"Referer": url}
data = {
"auth_token" : token,
"login-subject": username,
"password" : password,
}
response = self.request(url, method="POST", headers=headers, data=data)
if not response.history:
raise exception.AuthenticationError()
return self.cookies
def _extract_resource(self, page):
return util.json_loads(text.extr(
page, "CHV.obj.resource=", "};") + "}")
def _extract_user(self, page):
return self._extract_resource(page).get("user") or {}
def _pagination(self, page, endpoint, params):
data = None
seek, pos = text.extract(page, 'data-seek="', '"')
tokn, pos = text.extract(page, 'PF.obj.config.auth_token="', '"', pos)
params["action"] = "list"
params["list"] = "images"
params["sort"] = self.sort
params["seek"] = seek
params["page"] = 2
params["auth_token"] = tokn
while True:
for img in text.extract_iter(page, "data-object='", "'"):
yield util.json_loads(text.unquote(img))
if data:
if not data["seekEnd"] or params["seek"] == data["seekEnd"]:
return
params["seek"] = data["seekEnd"]
params["page"] += 1
elif not seek or 'class="pagination-next"' not in page:
return
data = self.request_json(endpoint, method="POST", data=params)
page = data["html"]
class ImgbbAlbumExtractor(ImgbbExtractor):
"""Extractor for albums on imgbb.com"""
subcategory = "album"
directory_fmt = ("{category}", "{user}", "{album_name} {album_id}")
pattern = r"(?:https?://)?ibb\.co/album/([^/?#]+)/?(?:\?([^#]+))?"
example = "https://ibb.co/album/ID"
def __init__(self, match):
ImgbbExtractor.__init__(self, match)
self.album_name = None
self.album_id = match[1]
self.sort = text.parse_query(match[2]).get("sort", "date_desc")
self.page_url = "https://ibb.co/album/" + self.album_id
def metadata(self, page):
album = text.extr(page, '"og:title" content="', '"')
user = self._extract_user(page)
return {
"album_id" : self.album_id,
"album_name" : text.unescape(album),
"user" : user.get("username") or "",
"user_id" : user.get("id") or "",
"displayname": user.get("name") or "",
}
def images(self, page):
url = text.extr(page, '"og:url" content="', '"')
album_id = url.rpartition("/")[2].partition("?")[0]
return self._pagination(page, "https://ibb.co/json", {
"from" : "album",
"albumid" : album_id,
"params_hidden[list]" : "images",
"params_hidden[from]" : "album",
"params_hidden[albumid]": album_id,
})
class ImgbbUserExtractor(ImgbbExtractor):
"""Extractor for user profiles in imgbb.com"""
subcategory = "user"
pattern = r"(?:https?://)?([\w-]+)\.imgbb\.com/?(?:\?([^#]+))?$"
example = "https://USER.imgbb.com"
def __init__(self, match):
ImgbbExtractor.__init__(self, match)
self.user = match[1]
self.sort = text.parse_query(match[2]).get("sort", "date_desc")
self.page_url = f"https://{self.user}.imgbb.com/"
def metadata(self, page):
user = self._extract_user(page)
return {
"user" : user.get("username") or self.user,
"user_id" : user.get("id") or "",
"displayname": user.get("name") or "",
}
def images(self, page):
user = text.extr(page, '.obj.resource={"id":"', '"')
return self._pagination(page, self.page_url + "json", {
"from" : "user",
"userid" : user,
"params_hidden[userid]": user,
"params_hidden[from]" : "user",
})
class ImgbbImageExtractor(ImgbbExtractor):
subcategory = "image"
pattern = r"(?:https?://)?ibb\.co/(?!album/)([^/?#]+)"
example = "https://ibb.co/ID"
def __init__(self, match):
ImgbbExtractor.__init__(self, match)
self.image_id = match[1]
def items(self):
url = "https://ibb.co/" + self.image_id
page = self.request(url).text
extr = text.extract_from(page)
user = self._extract_user(page)
image = {
"id" : self.image_id,
"title" : text.unescape(extr(
'"og:title" content="', ' hosted at ImgBB"')),
"url" : extr('"og:image" content="', '"'),
"width" : text.parse_int(extr('"og:image:width" content="', '"')),
"height": text.parse_int(extr('"og:image:height" content="', '"')),
"user" : user.get("username") or "",
"user_id" : user.get("id") or "",
"displayname": user.get("name") or "",
}
image["extension"] = text.ext_from_url(image["url"])
yield Message.Directory, image
yield Message.Url, image["url"], image
|
